def main():
pagedict = {
"title": "",
'screen_size': "",
'camera_res': "",
'screen_resolution': "",
'battery_capacity': "",
'ram': "",
'internal_memory': "",
'processor_speed': "",
'weight': "",
"body": ""
}
n = 0
p = Path('files_new/')
for folder in p.iterdir():
print(f"Converting folder: {folder.name}...")
if folder.is_dir():
for file in folder.iterdir():
if file.is_file() and file.name.endswith(".html"):
soup = getsoup(file)
specs = specsection(soup)
for spec_name, rx in regexes.items():
pagedict[spec_name] = getspec(specs, rx)
pagedict["title"] = getsouptitle(soup)
pagedict["body"] = getbodytext(soup)
qtd_specs = [*filter(lambda val: val, pagedict.values())]
if len(qtd_specs) < 8:
print(f"skiped {file.name}")
continue
xml = dicttoxml(pagedict,
attr_type=None,
custom_root="page")
prettyxml = parseString(xml).toprettyxml()
print(f"Writing file: {file.name}")
write_to_file(prettyxml, f'{n}.xml')
n += 1
print(f"Done with {folder.name}!")
print("Finished")
def main():
soup = getsoup(PATH)
cleansoup = preprocess(soup)
specs = getspecs(cleansoup)
print(specs)
def main():
soup = getsoup(SPEC_PAGE)
cleansoup = preprocess(soup)
getspecs(cleansoup)
def main():
soup = getsoup(PHONE_SPECS_PAGE)
cleansoup = preprocess(soup)
specs = cleansoup.find_all(class_="techspecs-section")
specsdict = getspecs(specs)
print(specsdict)
def main():
soup = getsoup(SPEC_PAGE)
cleansoup = preprocess(soup)
items = cleansoup.find_all(class_="tech_spec_wrap spec_toggle")
specs = getspecs(items)
print(specs)